US20070267495A1 - Frequency domain based micr reader - Google Patents
Frequency domain based micr reader Download PDFInfo
- Publication number
- US20070267495A1 US20070267495A1 US11/383,859 US38385906A US2007267495A1 US 20070267495 A1 US20070267495 A1 US 20070267495A1 US 38385906 A US38385906 A US 38385906A US 2007267495 A1 US2007267495 A1 US 2007267495A1
- Authority
- US
- United States
- Prior art keywords
- fourier components
- micr
- character
- fourier
- inputted
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06K—GRAPHICAL DATA READING; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
- G06K7/00—Methods or arrangements for sensing record carriers, e.g. for reading patterns
- G06K7/08—Methods or arrangements for sensing record carriers, e.g. for reading patterns by means detecting the change of an electrostatic or magnetic field, e.g. by detecting change of capacitance between electrodes
- G06K7/082—Methods or arrangements for sensing record carriers, e.g. for reading patterns by means detecting the change of an electrostatic or magnetic field, e.g. by detecting change of capacitance between electrodes using inductive or magnetic sensors
- G06K7/083—Methods or arrangements for sensing record carriers, e.g. for reading patterns by means detecting the change of an electrostatic or magnetic field, e.g. by detecting change of capacitance between electrodes using inductive or magnetic sensors inductive
- G06K7/084—Methods or arrangements for sensing record carriers, e.g. for reading patterns by means detecting the change of an electrostatic or magnetic field, e.g. by detecting change of capacitance between electrodes using inductive or magnetic sensors inductive sensing magnetic material by relative movement detecting flux changes without altering its magnetised state
Definitions
- the invention relates generally to MICR (magnetic ink character recognition), and more particularly, to a system and method for implementing a frequency domain based MICR reader.
- MICR magnetic ink character recognition
- MICR magnetic ink character recognition
- Single gap MICR readers which are vastly popular in check processing applications, utilize technology that transduces characters based on temporal signals from a single gap magnetic read-head. Such readers typically implement refined signal processing to improve the accuracy of the read. However, such systems are still vulnerable to noise that can interfere with their character discrimination capabilities.
- the present invention addresses the above-mentioned problems, as well as others, by providing a system and method for implementing a frequency domain based MICR reader.
- the invention provides a frequency domain based magnetic ink character recognition (MICR) system, comprising: a segmentation system for segmenting inputted MICR data into sets of temporal data for inputted characters; a Fourier system for generating a set of Fourier components from temporal data for an inputted character; a normalization system for normalizing the set of Fourier components to generate a normalized set of Fourier components; and a matching system for comparing the normalized set of Fourier components with each of a set of reference waveforms to determine an identity of the inputted character.
- MICR magnetic ink character recognition
- the invention provides a computer program product stored on a computer usable medium for implementing a frequency domain based magnetic ink character recognition (MICR) system, comprising: program code configured for generating a set of Fourier components from temporal MICR data for an inputted arbitrary character; program code configured for normalizing the set of Fourier components to generate a normalized set of Fourier components; and program code configured for comparing the normalized set of Fourier components with each of a set of reference waveforms to determine an identity of the inputted arbitrary character.
- MICR magnetic ink character recognition
- the invention provides a method of implementing a frequency domain based magnetic ink character recognition (MICR) system, comprising: generating a set of Fourier components from temporal MICR data for an inputted arbitrary character; normalizing the set of Fourier components to generate a normalized set of Fourier components; and comparing the normalized set of Fourier components with each of a set of reference waveforms to determine an identity of the inputted arbitrary character.
- MICR magnetic ink character recognition
- the invention provides a method for deploying an application for implementing a frequency domain based magnetic ink character recognition (MICR) system, comprising: providing a computer infrastructure being operable to: generate a set of Fourier components from temporal MICR data for an inputted arbitrary character; normalize the set of Fourier components to generate a normalized set of Fourier components; and compare the normalized set of Fourier components with each of a set of reference waveforms to determine an identity of the inputted arbitrary character.
- MICR magnetic ink character recognition
- reference waveform refers to a “set of reference Fourier components.”
- FIG. 1 depicts a frequency domain based MICR reader system in accordance with an embodiment of the present invention.
- FIG. 2 depicts a typical MICR signal in the temporal domain.
- FIG. 3 depicts an expanded view of a portion of the MICR signal of FIG. 2 showing three characters.
- FIG. 4 depicts a waveform of a single character broken down into a set of Fourier components in accordance with an embodiment of the present invention.
- FIG. 5 depicts a set of superimposed waveforms utilized to create a reference waveform for a character in accordance with an embodiment of the present invention.
- FIG. 6 depicts a resulting reference waveform for the character “0” generated in accordance with an embodiment of the present invention.
- FIG. 7 depicts a set of waveforms utilized to provide a matching operation in accordance with an embodiment of the present invention.
- FIG. 8 depicts a plot for determining a closest match between an inputted character and a known character set.
- FIG. 1 depicts a computer system 10 having a frequency domain based MICR system 18 that processes inputted MICR data 32 and generates recognized character data 34 .
- MICR data 32 general includes temporal waveform signals obtained from a MICR reader 36 that reads characters printed with magnetic ink, such as those found on the code line of a bank check. For instance, in the case of a single gap MICR reader, magnetic data is collected as the “gap” passes over the code line. In one common, but not limiting, application, code lines are printed using 14 possible characters (0-9 and four special characters) in E13B font.
- FIG. 2 depicts an example of a temporal waveform obtained from a MICR reader 36 from of a sample bank check having 27 characters in the code line.
- FIG. 3 depicts a segmented waveform view of three of the characters from the waveform of FIG. 2 .
- frequency domain based MICR system 18 ( FIG. 1 ) includes: a segmentation system 20 that segments the temporal MICR data 32 into individual character data; a Fourier system 22 that converts the individual character data into a set of Fourier components; a normalization system 24 that normalizes the magnitudes of the Fourier components for each character; a matching system 26 that compares the normalized set of Fourier components with a set of reference waveforms 31 representative of a set of possible characters; and a reference generation system 28 for generating the set of reference waveforms 31 .
- reference waveform 31 refers to a “set of reference Fourier components” (i.e., each reference waveform 31 includes a set of discrete values, as opposed to a continuous waveform).
- FIG. 4 depicts the first 20 frequency components of the character “2” after being read by the MICR reader 36 , segmented by segmentation system 20 , and converted to the frequency domain by Fourier system 22 .
- the magnitudes of the amplitudes of the components have been normalized by normalization system 24 such that the sum of the magnitudes of all of the 20 components equals 100.
- normalization system 24 any now known or later developed technique for segmenting the MICR data 32 and converting it to the frequency domain may be utilized.
- this illustrative embodiment normalizes twenty components by having their sums equal 100, any number of Fourier components could be used and any methodology for normalizing the components could be utilized.
- FIG. 5 depicts 20 superimposed versions of the Fourier components for the character “2.” This illustrates that for a given character, the magnetic information is mostly contained in the first six harmonic components (i.e., the fundamental harmonic and the following five harmonics). The sixth harmonic component, and beyond, are largely influenced by noise. Similar behavior is observed for all fourteen E13B characters. Accordingly, in one illustrative embodiment, filter 23 ( FIG. 1 ) eliminates the higher frequency components such that, e.g., only the first six Fourier components of an inputted character are taken into consideration when attempting to recognize the character. Obviously, the specific number components used may vary without departing from the scope of the invention. Regardless of the number used, the magnitudes should be normalized as described above.
- a reference generation system 28 is provided to generate a set of reference waveforms 31 (or “profiles”) for each possible character. For instance, in the case of E13B there are 14 possible characters, so 14 different reference waveforms 31 would be required. The reference waveforms 31 would only need to be generated once and could for example be stored in database 30 . In an alternative embodiment, the reference waveforms 31 could be obtained from a third party source, e.g., downloaded over a network. Regardless of how they are obtained, the reference waveforms 31 are ultimately used by matching system 26 to identify inputted (arbitrary) character waveforms.
- each reference waveform 31 may be generated by taking an average of N sample waveforms. For instance, as shown in FIG. 5 , there are 20 waveforms collected for the character “2.” An average of each Fourier component could be readily calculated to create a reference waveform 31 .
- FIG. 6 depicts a reference waveform 40 made up of the first six normalized Fourier components (referred to herein as a “golden reference”) for the character “0.”
- a golden reference for the character “0.”
- 14 such golden references would be generated.
- These golden references could then be compared with an inputted character waveform (i.e., an arbitrary character's Fourier spectrum) by matching system 26 to determine the identity of the inputted character waveform.
- an inputted character waveform would be matched against each of the 14 possible reference waveforms 31 .
- the first six normalized Fourier components of the inputted character waveform would be compared to each of the six normalized Fourier components of the 14 golden references.
- matching system 26 finds a closest match by calculating an absolute of the difference between the arbitrary character's spectrum and each golden reference.
- FIG. 7 depicts an example of such a comparison.
- a random character's waveform 42 is compared to the golden reference 40 of the character “0” to generate a difference 44 .
- An absolute value or magnitude for each comparison can, for instance, be obtained according the equation:
- ⁇ Diff_GR k corresponds to the summation of absolute amplitude differences against a known golden reference GR k .
- weighting factors 25 may be assigned to the different harmonics that make up the Fourier components in accordance with the summation equation described above. In general, because the lower harmonics incorporate less noise, they can be weighed more heavily when calculating the summation.
- concavity matching 27 could also be used to calculate or further enhance the matching process.
- Concavity matching 27 examines the Fourier components to identify local peaks and valleys, and then assesses penalties or bonuses when comparing waveforms of the two waveforms being analyzed. For example, in FIG. 7 , it can be seen that there is a local valley at the fourth Fourier component of the golden reference waveform 40 . Conversely, the fourth component of the random character waveform 42 includes a local peak. Thus, a penalty could be assessed by concavity matching 27 when comparing these two waveforms. Conversely, if both the reference waveform and the waveform of the unknown character include a local valley at the same harmonic, then concavity matching 27 could apply a bonus.
- FIG. 8 depicts a plot of the resulting comparison operations for two arbitrary inputted characters. As can be seen, of the 14 possible “matches,” both arbitrary inputted characters most closely match the character “0” Namely, the magnitude of the difference between the inputted characters and “0” is less than 10, while the magnitude of the difference for the remaining 13 characters ranges from 40 to over 90. Read rules can be readily established to offer best read rate and error rate performance.
- Computer system 10 of FIG. 1 may comprise any type of computing system, and could be implemented as part of a client and/or a server.
- Computer system 10 generally includes a processor 12 , input/output (I/O) 14 , memory 16 , and bus 17 .
- the processor 12 may comprise a single processing unit, or be distributed across one or more processing units in one or more locations, e.g., on a client and server.
- Memory 16 may comprise any known type of data storage and/or transmission media, including magnetic media, optical media, random access memory (RAM), read-only memory (ROM), a data cache, a data object, etc.
- memory 16 may reside at a single physical location, comprising one or more types of data storage, or be distributed across a plurality of physical systems in various forms.
- I/O 14 may comprise any system for exchanging information to/from an external resource.
- External devices/resources may comprise any known type of external device, including a monitor/display, speakers, storage, another computer system, a hand-held device, keyboard, mouse, voice recognition system, speech output system, printer, facsimile, pager, etc.
- Bus 17 provides a communication link between each of the components in the computer system 10 and likewise may comprise any known type of transmission link, including electrical, optical, wireless, etc.
- additional components such as cache memory, communication systems, system software, etc., may be incorporated into computer system 10 .
- Access to computer system 10 may be provided over a network such as the Internet, a local area network (LAN), a wide area network (WAN), a virtual private network (VPN), etc. Communication could occur via a direct hardwired connection (e.g., serial port), or via an addressable connection that may utilize any combination of wireline and/or wireless transmission methods. Moreover, conventional network connectivity, such as Token Ring, Ethernet, WiFi or other conventional communications standards could be used. Still yet, connectivity could be provided by conventional TCP/IP sockets-based protocol. In this instance, an Internet service provider could be used to establish interconnectivity. Further, as indicated above, communication could occur in a client-server or server-server environment.
- LAN local area network
- WAN wide area network
- VPN virtual private network
- a computer system 10 comprising a frequency domain MICR system 18 could be created, maintained and/or deployed by a service provider that offers the functions described herein for customers. That is, a service provider could offer to provide frequency based character recognition as described above.
- systems, functions, mechanisms, methods, engines and modules described herein can be implemented in hardware, software, or a combination of hardware and software. They may be implemented by any type of computer system or other apparatus adapted for carrying out the methods described herein.
- a typical combination of hardware and software could be a general-purpose computer system with a computer program that, when loaded and executed, controls the computer system such that it carries out the methods described herein.
- a specific use computer containing specialized hardware for carrying out one or more of the functional tasks of the invention could be utilized.
- part or all of the invention could be implemented in a distributed manner, e.g., over a network such as the Internet.
- the present invention can also be embedded in a computer program product, which comprises all the features enabling the implementation of the methods and functions described herein, and which—when loaded in a computer system—is able to carry out these methods and functions.
- Terms such as computer program, software program, program, program product, software, etc., in the present context mean any expression, in any language, code or notation, of a set of instructions intended to cause a system having an information processing capability to perform a particular function either directly or after either or both of the following: (a) conversion to another language, code or notation; and/or (b) reproduction in a different material form.
Landscapes
- Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Character Input (AREA)
Abstract
Description
- The invention relates generally to MICR (magnetic ink character recognition), and more particularly, to a system and method for implementing a frequency domain based MICR reader.
- MICR (magnetic ink character recognition) technology is commonly deployed by banks and other financial institutions for reading code line character data, such as account and routing information typically found on bank checks. Because MICR utilizes magnetic, as opposed to optical, information to read character data, MICR readers are generally immune to optical noise.
- Single gap MICR readers, which are vastly popular in check processing applications, utilize technology that transduces characters based on temporal signals from a single gap magnetic read-head. Such readers typically implement refined signal processing to improve the accuracy of the read. However, such systems are still vulnerable to noise that can interfere with their character discrimination capabilities.
- Accordingly, a need exists for a system and method that provide improved read capabilities for a MICR reader.
- The present invention addresses the above-mentioned problems, as well as others, by providing a system and method for implementing a frequency domain based MICR reader.
- In a first aspect, the invention provides a frequency domain based magnetic ink character recognition (MICR) system, comprising: a segmentation system for segmenting inputted MICR data into sets of temporal data for inputted characters; a Fourier system for generating a set of Fourier components from temporal data for an inputted character; a normalization system for normalizing the set of Fourier components to generate a normalized set of Fourier components; and a matching system for comparing the normalized set of Fourier components with each of a set of reference waveforms to determine an identity of the inputted character.
- In a second aspect, the invention provides a computer program product stored on a computer usable medium for implementing a frequency domain based magnetic ink character recognition (MICR) system, comprising: program code configured for generating a set of Fourier components from temporal MICR data for an inputted arbitrary character; program code configured for normalizing the set of Fourier components to generate a normalized set of Fourier components; and program code configured for comparing the normalized set of Fourier components with each of a set of reference waveforms to determine an identity of the inputted arbitrary character.
- In a third aspect, the invention provides a method of implementing a frequency domain based magnetic ink character recognition (MICR) system, comprising: generating a set of Fourier components from temporal MICR data for an inputted arbitrary character; normalizing the set of Fourier components to generate a normalized set of Fourier components; and comparing the normalized set of Fourier components with each of a set of reference waveforms to determine an identity of the inputted arbitrary character.
- In a fourth aspect, the invention provides a method for deploying an application for implementing a frequency domain based magnetic ink character recognition (MICR) system, comprising: providing a computer infrastructure being operable to: generate a set of Fourier components from temporal MICR data for an inputted arbitrary character; normalize the set of Fourier components to generate a normalized set of Fourier components; and compare the normalized set of Fourier components with each of a set of reference waveforms to determine an identity of the inputted arbitrary character.
- Accordingly, by analyzing the Fourier components, an arbitrary character can be read by correlating the amplitude data of the Fourier components to reference waveforms. This approach offers automatic noise immunity since any noise is typically found in the higher frequencies which can be easily filtered out. Note that for the purposes of this disclosure, the term “reference waveform” refers to a “set of reference Fourier components.”
- These and other features of this invention will be more readily understood from the following detailed description of the various aspects of the invention taken in conjunction with the accompanying drawings in which:
-
FIG. 1 depicts a frequency domain based MICR reader system in accordance with an embodiment of the present invention. -
FIG. 2 depicts a typical MICR signal in the temporal domain. -
FIG. 3 depicts an expanded view of a portion of the MICR signal ofFIG. 2 showing three characters. -
FIG. 4 depicts a waveform of a single character broken down into a set of Fourier components in accordance with an embodiment of the present invention. -
FIG. 5 depicts a set of superimposed waveforms utilized to create a reference waveform for a character in accordance with an embodiment of the present invention. -
FIG. 6 depicts a resulting reference waveform for the character “0” generated in accordance with an embodiment of the present invention. -
FIG. 7 depicts a set of waveforms utilized to provide a matching operation in accordance with an embodiment of the present invention. -
FIG. 8 depicts a plot for determining a closest match between an inputted character and a known character set. - Referring now to the drawings,
FIG. 1 depicts acomputer system 10 having a frequency domain basedMICR system 18 that processes inputtedMICR data 32 and generates recognizedcharacter data 34.MICR data 32 general includes temporal waveform signals obtained from aMICR reader 36 that reads characters printed with magnetic ink, such as those found on the code line of a bank check. For instance, in the case of a single gap MICR reader, magnetic data is collected as the “gap” passes over the code line. In one common, but not limiting, application, code lines are printed using 14 possible characters (0-9 and four special characters) in E13B font.FIG. 2 depicts an example of a temporal waveform obtained from aMICR reader 36 from of a sample bank check having 27 characters in the code line.FIG. 3 depicts a segmented waveform view of three of the characters from the waveform ofFIG. 2 . - Rather than analyze the waveform data in the temporal domain to perform character recognition, the present invention converts the
MICR data 32 into the frequency domain to perform character recognition. To achieve this, frequency domain based MICR system 18 (FIG. 1 ) includes: asegmentation system 20 that segments thetemporal MICR data 32 into individual character data; a Fouriersystem 22 that converts the individual character data into a set of Fourier components; anormalization system 24 that normalizes the magnitudes of the Fourier components for each character; amatching system 26 that compares the normalized set of Fourier components with a set ofreference waveforms 31 representative of a set of possible characters; and areference generation system 28 for generating the set ofreference waveforms 31. Note that for the purposes of this disclosure, the term “reference waveform 31” refers to a “set of reference Fourier components” (i.e., eachreference waveform 31 includes a set of discrete values, as opposed to a continuous waveform). -
FIG. 4 depicts the first 20 frequency components of the character “2” after being read by theMICR reader 36, segmented bysegmentation system 20, and converted to the frequency domain by Fouriersystem 22. In addition, the magnitudes of the amplitudes of the components have been normalized bynormalization system 24 such that the sum of the magnitudes of all of the 20 components equals 100. Note that any now known or later developed technique for segmenting theMICR data 32 and converting it to the frequency domain may be utilized. In addition, although this illustrative embodiment normalizes twenty components by having their sums equal 100, any number of Fourier components could be used and any methodology for normalizing the components could be utilized. -
FIG. 5 depicts 20 superimposed versions of the Fourier components for the character “2.” This illustrates that for a given character, the magnetic information is mostly contained in the first six harmonic components (i.e., the fundamental harmonic and the following five harmonics). The sixth harmonic component, and beyond, are largely influenced by noise. Similar behavior is observed for all fourteen E13B characters. Accordingly, in one illustrative embodiment, filter 23 (FIG. 1 ) eliminates the higher frequency components such that, e.g., only the first six Fourier components of an inputted character are taken into consideration when attempting to recognize the character. Obviously, the specific number components used may vary without departing from the scope of the invention. Regardless of the number used, the magnitudes should be normalized as described above. - A noted above with regard to
FIG. 1 , areference generation system 28 is provided to generate a set of reference waveforms 31 (or “profiles”) for each possible character. For instance, in the case of E13B there are 14 possible characters, so 14different reference waveforms 31 would be required. Thereference waveforms 31 would only need to be generated once and could for example be stored indatabase 30. In an alternative embodiment, thereference waveforms 31 could be obtained from a third party source, e.g., downloaded over a network. Regardless of how they are obtained, thereference waveforms 31 are ultimately used by matchingsystem 26 to identify inputted (arbitrary) character waveforms. - In one illustrative embodiment, each
reference waveform 31 may be generated by taking an average of N sample waveforms. For instance, as shown inFIG. 5 , there are 20 waveforms collected for the character “2.” An average of each Fourier component could be readily calculated to create areference waveform 31. -
FIG. 6 depicts areference waveform 40 made up of the first six normalized Fourier components (referred to herein as a “golden reference”) for the character “0.” Thus, in the case of E13B, 14 such golden references would be generated. These golden references could then be compared with an inputted character waveform (i.e., an arbitrary character's Fourier spectrum) by matchingsystem 26 to determine the identity of the inputted character waveform. Thus, in the case of E13B, an inputted character waveform would be matched against each of the 14possible reference waveforms 31. Namely, the first six normalized Fourier components of the inputted character waveform would be compared to each of the six normalized Fourier components of the 14 golden references. - In one illustrative methodology, matching
system 26 finds a closest match by calculating an absolute of the difference between the arbitrary character's spectrum and each golden reference.FIG. 7 depicts an example of such a comparison. In this case, a random character'swaveform 42 is compared to thegolden reference 40 of the character “0” to generate adifference 44. An absolute value or magnitude for each comparison can, for instance, be obtained according the equation: -
Σ{Diff — GR k }i=Σ|(GoldRef k)i−RandomChar i| - where i varies from 1 to 6 and where Σ Diff_GRk corresponds to the summation of absolute amplitude differences against a known golden reference GRk.
- Additional modifications or implementations that can be used when matching Fourier component sets include the use of
weighting factors 25 and the use of concavity matching 27. For instance, in one illustrative embodiment,different weighting factors 25 may be assigned to the different harmonics that make up the Fourier components in accordance with the summation equation described above. In general, because the lower harmonics incorporate less noise, they can be weighed more heavily when calculating the summation. Thus for instance, the absolute amplitude difference for the first Fourier harmonic i=1 could be weighted by the highest factor (e.g., 2), while the absolute amplitude difference for i=2 could be weighted by a lesser factor (e.g., 1.8), and the absolute amplitude difference for i=3 could be weighted by even a lesser factor (e.g., 1.6), and so on. - In a further illustrative embodiment, concavity matching 27 could also be used to calculate or further enhance the matching process. Concavity matching 27 examines the Fourier components to identify local peaks and valleys, and then assesses penalties or bonuses when comparing waveforms of the two waveforms being analyzed. For example, in
FIG. 7 , it can be seen that there is a local valley at the fourth Fourier component of thegolden reference waveform 40. Conversely, the fourth component of therandom character waveform 42 includes a local peak. Thus, a penalty could be assessed by concavity matching 27 when comparing these two waveforms. Conversely, if both the reference waveform and the waveform of the unknown character include a local valley at the same harmonic, then concavity matching 27 could apply a bonus. - As noted, in the case of E13B, 14 different compare operations would be required to find a closest match since there are 14 possible characters.
FIG. 8 depicts a plot of the resulting comparison operations for two arbitrary inputted characters. As can be seen, of the 14 possible “matches,” both arbitrary inputted characters most closely match the character “0” Namely, the magnitude of the difference between the inputted characters and “0” is less than 10, while the magnitude of the difference for the remaining 13 characters ranges from 40 to over 90. Read rules can be readily established to offer best read rate and error rate performance. - It is understood that this is but one example of a pattern matching methodology, and any other now known or later developed methodology could be employed without departing from the scope of the invention. It should also be understood that while the invention is generally described with reference to a system and method for reading E13B data, the invention is not limited to any particular font or character set.
- Note that
computer system 10 ofFIG. 1 may comprise any type of computing system, and could be implemented as part of a client and/or a server.Computer system 10 generally includes aprocessor 12, input/output (I/O) 14,memory 16, andbus 17. Theprocessor 12 may comprise a single processing unit, or be distributed across one or more processing units in one or more locations, e.g., on a client and server.Memory 16 may comprise any known type of data storage and/or transmission media, including magnetic media, optical media, random access memory (RAM), read-only memory (ROM), a data cache, a data object, etc. Moreover,memory 16 may reside at a single physical location, comprising one or more types of data storage, or be distributed across a plurality of physical systems in various forms. - I/
O 14 may comprise any system for exchanging information to/from an external resource. External devices/resources may comprise any known type of external device, including a monitor/display, speakers, storage, another computer system, a hand-held device, keyboard, mouse, voice recognition system, speech output system, printer, facsimile, pager, etc.Bus 17 provides a communication link between each of the components in thecomputer system 10 and likewise may comprise any known type of transmission link, including electrical, optical, wireless, etc. Although not shown, additional components, such as cache memory, communication systems, system software, etc., may be incorporated intocomputer system 10. - Access to
computer system 10 may be provided over a network such as the Internet, a local area network (LAN), a wide area network (WAN), a virtual private network (VPN), etc. Communication could occur via a direct hardwired connection (e.g., serial port), or via an addressable connection that may utilize any combination of wireline and/or wireless transmission methods. Moreover, conventional network connectivity, such as Token Ring, Ethernet, WiFi or other conventional communications standards could be used. Still yet, connectivity could be provided by conventional TCP/IP sockets-based protocol. In this instance, an Internet service provider could be used to establish interconnectivity. Further, as indicated above, communication could occur in a client-server or server-server environment. - It should be appreciated that the teachings of the present invention could be offered as a business method on a subscription or fee basis. For example, a
computer system 10 comprising a frequencydomain MICR system 18 could be created, maintained and/or deployed by a service provider that offers the functions described herein for customers. That is, a service provider could offer to provide frequency based character recognition as described above. - It is understood that the systems, functions, mechanisms, methods, engines and modules described herein can be implemented in hardware, software, or a combination of hardware and software. They may be implemented by any type of computer system or other apparatus adapted for carrying out the methods described herein. A typical combination of hardware and software could be a general-purpose computer system with a computer program that, when loaded and executed, controls the computer system such that it carries out the methods described herein. Alternatively, a specific use computer, containing specialized hardware for carrying out one or more of the functional tasks of the invention could be utilized. In a further embodiment, part or all of the invention could be implemented in a distributed manner, e.g., over a network such as the Internet.
- The present invention can also be embedded in a computer program product, which comprises all the features enabling the implementation of the methods and functions described herein, and which—when loaded in a computer system—is able to carry out these methods and functions. Terms such as computer program, software program, program, program product, software, etc., in the present context mean any expression, in any language, code or notation, of a set of instructions intended to cause a system having an information processing capability to perform a particular function either directly or after either or both of the following: (a) conversion to another language, code or notation; and/or (b) reproduction in a different material form.
- The foregoing description of the invention has been presented for purposes of illustration and description. It is not intended to be exhaustive or to limit the invention to the precise form disclosed, and obviously, many modifications and variations are possible. Such modifications and variations that may be apparent to a person skilled in the art are intended to be included within the scope of this invention as defined by the accompanying claims.
Claims (25)
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US11/383,859 US7796798B2 (en) | 2006-05-17 | 2006-05-17 | Frequency domain based MICR reader |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US11/383,859 US7796798B2 (en) | 2006-05-17 | 2006-05-17 | Frequency domain based MICR reader |
Publications (2)
Publication Number | Publication Date |
---|---|
US20070267495A1 true US20070267495A1 (en) | 2007-11-22 |
US7796798B2 US7796798B2 (en) | 2010-09-14 |
Family
ID=38711131
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US11/383,859 Expired - Fee Related US7796798B2 (en) | 2006-05-17 | 2006-05-17 | Frequency domain based MICR reader |
Country Status (1)
Country | Link |
---|---|
US (1) | US7796798B2 (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2011143998A1 (en) | 2010-05-18 | 2011-11-24 | 山东新北洋信息技术股份有限公司 | Method, device and system for recognizing magnetic ink characters |
Families Citing this family (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US8023719B2 (en) * | 2007-08-15 | 2011-09-20 | International Business Machines Corporation | MICR reader using phase angle extracted from frequency domain analysis |
US8917272B2 (en) * | 2009-09-30 | 2014-12-23 | Mckesson Financial Holdings | Methods, apparatuses, and computer program products for facilitating visualization and analysis of medical data |
Citations (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US3599147A (en) * | 1967-09-12 | 1971-08-10 | Nat Res Dev | Character recognition systems and apparatus |
US3846752A (en) * | 1972-10-02 | 1974-11-05 | Hitachi Ltd | Character recognition apparatus |
US4356472A (en) * | 1980-06-27 | 1982-10-26 | International Business Machines Corporation | Character recognition system |
US4454610A (en) * | 1978-05-19 | 1984-06-12 | Transaction Sciences Corporation | Methods and apparatus for the automatic classification of patterns |
US4764973A (en) * | 1986-05-28 | 1988-08-16 | The United States Of America As Represented By The Secretary Of The Air Force | Whole word, phrase or number reading |
US4770184A (en) * | 1985-12-17 | 1988-09-13 | Washington Research Foundation | Ultrasonic doppler diagnostic system using pattern recognition |
US4817176A (en) * | 1986-02-14 | 1989-03-28 | William F. McWhortor | Method and apparatus for pattern recognition |
US4817178A (en) * | 1985-04-15 | 1989-03-28 | Hitachi, Ltd. | Linear cursor representation method |
US5504318A (en) * | 1991-09-13 | 1996-04-02 | Symbol Technologies, Inc. | Analog waveform decoder using peak locations |
US5911013A (en) * | 1992-08-25 | 1999-06-08 | Canon Kabushiki Kaisha | Character recognition method and apparatus capable of handling handwriting |
US5932806A (en) * | 1994-12-13 | 1999-08-03 | The B.F. Goodrich Company | Contaminant detection system |
US6421457B1 (en) * | 1999-02-12 | 2002-07-16 | Applied Materials, Inc. | Process inspection using full and segment waveform matching |
US20060039580A1 (en) * | 2000-08-30 | 2006-02-23 | Moon Rodney G | Method and system for watermark detection |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPS60173685A (en) | 1984-02-06 | 1985-09-07 | Nippon Telegr & Teleph Corp <Ntt> | Method for segmenting character |
-
2006
- 2006-05-17 US US11/383,859 patent/US7796798B2/en not_active Expired - Fee Related
Patent Citations (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US3599147A (en) * | 1967-09-12 | 1971-08-10 | Nat Res Dev | Character recognition systems and apparatus |
US3846752A (en) * | 1972-10-02 | 1974-11-05 | Hitachi Ltd | Character recognition apparatus |
US4454610A (en) * | 1978-05-19 | 1984-06-12 | Transaction Sciences Corporation | Methods and apparatus for the automatic classification of patterns |
US4356472A (en) * | 1980-06-27 | 1982-10-26 | International Business Machines Corporation | Character recognition system |
US4817178A (en) * | 1985-04-15 | 1989-03-28 | Hitachi, Ltd. | Linear cursor representation method |
US4770184A (en) * | 1985-12-17 | 1988-09-13 | Washington Research Foundation | Ultrasonic doppler diagnostic system using pattern recognition |
US4817176A (en) * | 1986-02-14 | 1989-03-28 | William F. McWhortor | Method and apparatus for pattern recognition |
US4764973A (en) * | 1986-05-28 | 1988-08-16 | The United States Of America As Represented By The Secretary Of The Air Force | Whole word, phrase or number reading |
US5504318A (en) * | 1991-09-13 | 1996-04-02 | Symbol Technologies, Inc. | Analog waveform decoder using peak locations |
US5911013A (en) * | 1992-08-25 | 1999-06-08 | Canon Kabushiki Kaisha | Character recognition method and apparatus capable of handling handwriting |
US5932806A (en) * | 1994-12-13 | 1999-08-03 | The B.F. Goodrich Company | Contaminant detection system |
US6421457B1 (en) * | 1999-02-12 | 2002-07-16 | Applied Materials, Inc. | Process inspection using full and segment waveform matching |
US20060039580A1 (en) * | 2000-08-30 | 2006-02-23 | Moon Rodney G | Method and system for watermark detection |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2011143998A1 (en) | 2010-05-18 | 2011-11-24 | 山东新北洋信息技术股份有限公司 | Method, device and system for recognizing magnetic ink characters |
EP2573707A4 (en) * | 2010-05-18 | 2017-01-04 | Shandong New Beiyang Information Technology Co., Ltd. | Method, device and system for recognizing magnetic ink characters |
Also Published As
Publication number | Publication date |
---|---|
US7796798B2 (en) | 2010-09-14 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN113257255B (en) | Method and device for identifying forged voice, electronic equipment and storage medium | |
JP2006079479A (en) | Time series data determination method | |
Dalal et al. | Performance of integrated signature verification approach | |
CN113271292B (en) | Malicious domain name cluster detection method and device based on word vectors | |
Malallah et al. | Online handwritten signature recognition by length normalization using up-sampling and down-sampling | |
CN112435137A (en) | Cheating information detection method and system based on community mining | |
US7796798B2 (en) | Frequency domain based MICR reader | |
Juvonen et al. | Adaptive framework for network traffic classification using dimensionality reduction and clustering | |
EP1141943B1 (en) | Speaker recognition using spectrogram correlation | |
Hostiadi et al. | Hybrid model for bot group activity detection using similarity and correlation approaches based on network traffic flows analysis | |
CN115909422A (en) | Intelligent medical information management system and method thereof | |
Lee et al. | Improved segmentation through dynamic time warping for signature verification using a neural network classifier | |
Chaa et al. | Contactless person recognition using 2D and 3D finger knuckle patterns | |
US7865332B2 (en) | Scaled exponential smoothing for real time histogram | |
Velliangiri et al. | Detection of dos attacks in smart city networks with feature distance maps: A statistical approach | |
CN110233848B (en) | Asset situation analysis method and device | |
Alharbi et al. | Face-voice based multimodal biometric authentication system via FaceNet and GMM | |
CN115277205B (en) | Model training method and device and port risk identification method | |
US8023719B2 (en) | MICR reader using phase angle extracted from frequency domain analysis | |
US20080140468A1 (en) | Complex exponential smoothing for identifying patterns in business data | |
CN113706279B (en) | Fraud analysis method, fraud analysis device, electronic equipment and storage medium | |
Magazine et al. | Fake speech detection using modulation spectrogram | |
Chen et al. | A real-world online signature verification system based on correlation algorithm | |
Prashanth et al. | Iris Recognition using Bicubic Interpolation and Multi Level DWT Decomposition | |
Elias et al. | Extended adjacency and scale-dependent graph Fourier transform via diffusion distances |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
AS | Assignment |
Owner name: INTERNATIONAL BUSINESS MACHINES CORPORATION, NEW Y Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNOR:PRAKASH, RAVINDER;REEL/FRAME:017708/0590 Effective date: 20060516 |
|
REMI | Maintenance fee reminder mailed | ||
FPAY | Fee payment |
Year of fee payment: 4 |
|
SULP | Surcharge for late payment | ||
AS | Assignment |
Owner name: LINKEDIN CORPORATION, CALIFORNIA Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNOR:INTERNATIONAL BUSINESS MACHINES CORPORATION;REEL/FRAME:035201/0479 Effective date: 20140331 |
|
FEPP | Fee payment procedure |
Free format text: MAINTENANCE FEE REMINDER MAILED (ORIGINAL EVENT CODE: REM.) |
|
LAPS | Lapse for failure to pay maintenance fees |
Free format text: PATENT EXPIRED FOR FAILURE TO PAY MAINTENANCE FEES (ORIGINAL EVENT CODE: EXP.); ENTITY STATUS OF PATENT OWNER: LARGE ENTITY |
|
STCH | Information on status: patent discontinuation |
Free format text: PATENT EXPIRED DUE TO NONPAYMENT OF MAINTENANCE FEES UNDER 37 CFR 1.362 |
|
FP | Lapsed due to failure to pay maintenance fee |
Effective date: 20180914 |